Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    critical analysis terms related to storytelling, such as writing, dialogue, plot, graphics, pacing, and cinematography

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cot
    -0.83
    isance
    -0.73
    inel
    -0.72
    rolet
    -0.71
    IELD
    -0.69
    ģĸ
    -0.69
    vard
    -0.69
    iatus
    -0.68
    ewitness
    -0.67
    icer
    -0.67
    POSITIVE LOGITS
     quirks
    0.98
     varies
    0.94
     resemblance
    0.93
     aspect
    0.91
     resemb
    0.85
     inconsistencies
    0.83
     choices
    0.82
     itself
    0.80
     layout
    0.80
     disparity
    0.79
    Act Density 0.312%

    No Known Activations